Series Of Layers Research Articles

Multi-layered quasi-2D perovskite based triboelectric nanogenerator

Inorganic-organic perovskites are considered as one of the emerging candidates as a tribopositive material in triboelectric nanogenerators (TENG) owing to their unique functionalities. Among them, quasi-two-dimensional (quasi-2D) perovskites are promising materials for TENG due to layered nature, excellent environmental and chemical stability, tunability, and excellent electrical properties. Herein, we investigate the performance of TENG based on multiple series of perovskite layers using simple solution processing technique. The dimensionality of the perovskite layers is attained by changing the stoichiometric ratios of phenylethylammonium iodide (PEAI), lead iodide (PbI2), methylammonium iodide (MAI). The quasi-2D based TENG generates the maximum output electrical performance with a voltage of 306V, current of 4.71µA, and maximum power density of 3.48µW/cm2 at the optimum value of (<n> = 5) due to the higher concentration of C–N and N–H groups. Moreover, the fabricated device shows stable performance for 12000 cycles. The TENG device is further utilized to charge the various commercially available capacitors, for lightning of light-emitting diodes (LEDs), and to power up low-power electronic devices. These results demonstrate the effect of the dimensionality of perovskites on the output performance of the TENG for use in next-generation energy harnessing.

Nanoelectrospray based synthesis of large, transportable membranes with integrated membrane proteins

Membrane proteins tend to be difficult to study since they need to be integrated into a lipid bilayer membrane to function properly. This study presents a method to synthesize a macroscopically large and freely transportable membrane with integrated membrane proteins which is useful for studying membrane proteins and protein complexes in isolation. The method could serve as a blueprint for the production of larger quantities of functionalised membranes for integration into technical devices similar to the MinION DNA sequencer. It is possible to self-assemble larger biological membranes on solid surfaces. However, they cannot be removed from their solid support without destroying them. In transportable form, self-assembled membranes are limited to sizes of about 17 nm in nanodiscs. Here we electrospray a series of molecular layers onto the liquid surface of a buffer solution which creates a flat, liquid environment on the surface that directs the self-assembly of the membrane. This method enables us to experimentally control the membrane composition and to succeed in producing large membranes with integrated OmpG, a transmembrane pore protein. The technique is compatible with the assembly of membrane based protein complexes. Listeriolysin O and pneumolysin efficiently assemble into non-covalent membrane pore complexes of approximately 30 units or more within the surface layer.

Echo-free quality factor of a multilayer axion haloscope

We report a methodology to determine the quality factor (Q) of wavy dark matter detectors equipped with multilayered resonators, including Fabry-Pérot interferometers and the so-called dielectric haloscope. An anechoic chamber enables the observation of the resonance frequency and its amplitude for an unlimited series of layers for the first time, which is conveniently filtered. The frequency-normalized power enhancement measured in a Dark Photons and Axionlike Particles Interferometer (DALI) prototype is a few hundred per layer over a sweep bandwidth of a few dozen of megahertz. In light of this result, this scaled-down prototype is sensitive to axions saturating the local dark matter density with a coupling to photons between gaγγ≳10−12 and gaγγ≳few×10−14 GeV−1 at frequencies of several dozens of gigahertz once cooled down to the different working temperatures of the experiment and immersed in magnetic fields ranging from about 1 to 10 T; while the sensitivity of the full-scale DALI is projected at gaγγ≳few×10−15 GeV−1 over the entire 25–250 μeV range since Q≳104 is expected. Published by the American Physical Society 2024

Unveiling the Microscopic Origin of Ultrahigh Initial Coulombic Efficiency of High-Entropy Metal-Organic Frameworks for Sodium Storage.

The initial irreversible capacity loss during the first charging process largely reduces the affordable energy and power density of sodium storage devices, and developing advanced materials is the efficient way to solve this problem, which is fraught with challenges. Herein, inspired by theoretical calculations and the high-entropy concept, a series of fewer layers of high-entropy metal-organic frameworks (FLHE-MOFs) are successfully fabricated, delivering an ultrahigh initial Coulombic efficiency (ICE) of 86.1% and excellent cycling performance, which is far more than that of the other electrode materials (generally <70%). Greatly, the storage behavior of high-, medium-, and low-entropy MOFs is clarified by theoretical calculations and in-/ex-situ characterization, revealing that Co and Fe species can provide substantial sodium storage sites and largely enhance the charge transfer rate, whereas high-entropy effect can enable structural reversibility. Sodium ion capacitors constructed with FLHE-MOFs as the anode can provide an ultrahigh energy density of 121.8 W h kg-1 (200 W kg-1) and an extremely long-term cycle lifespan. This work not only breaks the limitation of MOF materials with poor performance for sodium storage but also provides an effective strategy for the fabrication and application of high-performance MOF-based anode materials with high ICE, in which this idea may also be applied in other fields.

Impact of surface hydrophilicity on the ordering and transport properties of bicontinuous microemulsions.

Microemulsions (MEs) have many industrial applications, where recent developments have shown that MEs can be utilized for electrochemical applications, including potentially in redox flow batteries. However, understanding the structure and dynamics of these systems, including at a surface, is needed to direct and rationally control their electrochemical behavior. While bulk solution measurements have provided insight into their structure, their assembly at an interface also impacts the electron (to the electrode) and ion (across the surfactant) charge transfer processes in the system. To address this shortcoming, neutron reflectivity experiments and molecular simulations have been completed that document the near surface structure of a series of deuterated water (D2O)/polysorbate-20/toluene MEs on hydrophilic and amphiphilic surfaces. These results show that the microemulsions form complex layered structures near a hard electrode surface, where most layers are not purely one component. Decreasing the D2O concentration in the ME increases the number of and purity of the layers established on the solid surface. These lamellar-type layers transition from the surface to the bulk microemulsion as a series of mixed layers (i.e., containing oil, water, and surfactant) that are consistent with perforated lamellae. Additionally, these mixed lamellae appear to become more perforated with oil and water pathways on an amphiphilic surface. The purity and thickness of these layers will influence the accessibility of an electrode by redox active species, as well as ion transport required to satisfy the electroneutrality condition.

Perspectives and Prospects for International Water Law in the ASEAN Region: Is There an ASEAN Way to Transboundary Water Cooperation Under International Law?

Around the world there are over 300 transboundary watercourses and around 500 transboundary groundwater bodies shared by two or more States. The Association of Southeast Asian Nations (ASEAN) region contains forty-one transboundary surface and groundwater bodies shared between ten ASEAN States and the five non-ASEAN States at its periphery. As transboundary water resources they are governed under international law found in a series of layers across a spectrum of bindingness (customary international law, global–regional–multilateral–bilateral agreements and non-binding instruments). Through an analysis of the international law relevant to the governance of transboundary water resources in the region, this study seeks to explore the ASEAN approach to transboundary water governance under international law. While this analysis finds that there is no uniform practice across the region, the paper concludes with possible paths forward for the legalization of transboundary water cooperation.

Exploring potential of lead-free KSn0.5Ge0.5I3 based perovskite solar cell: A combined first-principle DFT and SCAPS-1D study

Perovskite solar cells present a promising alternative to conventional silicon or lead-based solar cells, offering a synergistic blend of cost-effectiveness and potential for elevated power conversion efficiency. We investigated the potential of an innovative KSn0.5Ge0.5I3-based perovskite solar cell (PSC) using density functional theory (DFT) and SCAPS-1D simulation studies. Computational analysis via DFT probed the crystal structure, elastic, mechanical, and optoelectronic properties of KSn0.5Ge0.5I3. Tolerance factor computation (0.94) and negative formation energy (-3.16 eV) affirmed the thermodynamic stability of the orthorhombic phase in KSn0.5Ge0.5I3. Optical variables including refractive index, absorption coefficient, dielectric function, optical loss, and reflectivity, were computed to explore KSn0.5Ge0.5I3 viability in PV applications. Band structure analysis, density of states (DOS), and projected density of states (PDOS) have been used to determine the band gap (∼1.87 eV), effective masses, and mobility of e-/h+. We have conducted SCAPS-1D simulation for diverse PSCs configurations using various holes transport layers (HTLs) and electron transport layers (ETLs), identified IGZO (Eg = 3.05 eV) as a proficient ETL while CuSbS2 (Eg = 1.58 eV) as an effective HTL. A comprehensive investigation of parameters such as absorber layer thickness, shunt and series resistance, donor and acceptor density, absorber defect density, back contact metal, temperature, and interface characteristics was undertaken, and the impact on PV device performances was assessed through current-voltage (IV) and quantum efficiency (Q.E) characteristics curves. These findings underscore the potential of KSn0.5Ge0.5I3 as a promising material for PSCs, offering a sustainable and eco-friendly avenue for future renewable energy.

Enhanced detection of Aspergillus flavus in peanut kernels using a multi-scale attention transformer (MSAT): Advancements in food safety and contamination analysis

In this study, a multi-scale attention transformer (MSAT) was coupled with hyperspectral imaging for classifying peanut kernels contaminated with diverse Aspergillus flavus fungi. The results underscored that the MSAT significantly outperformed classic deep learning models, due to its sophisticated multi-scale attention mechanism which enhanced its classification capabilities. The multi-scale attention mechanism was utilized by employing several multi-head attention layers to focus on both fine-scale and broad-scale features. It also integrated a series of scale processing layers to capture features at different resolutions and incorporated a self-attention mechanism to integrate information across different levels. The MSAT model achieved outstanding performance in different classification tasks, particularly in distinguishing healthy peanut kernels from those contaminated with aflatoxigenic fungi, with test accuracy achieving 98.42±0.22%. However, it faced challenges in differentiating peanut kernels contaminated with aflatoxigenic fungi from those with non-aflatoxigenic contamination. Visualization of attention weights explicitly revealed that the MSAT model's multi-scale attention mechanism progressively refined its focus from broad spatial-spectral features to more specialized signatures. Overall, the MSAT model's advanced processing capabilities marked a notable advancement in the field of food quality safety, offering a robust and reliable tool for the rapid and accurate detection of Aspergillus flavus contaminations in food.

Numerical simulations on compression behaviors of the laminated shale based on the digital image technology and the discrete element method

As an unconventional reservoir sedimentary rock, shale contains a series of layers and various microstructures that lead to complex mechanical properties, such as the anisotropy of stiffness and strength. This study is directed towards the anisotropy caused by the microstructures of the shale, employing the 2D particle flow code (PFC2D) to explore stiffness, strength, failure mode, and micro-crack evolution. More realistic microstructures and the calibration of microscopic parameters of the shale are reasonably considered through the computed tomography (CT) images and mineral analysis. The corresponding numerical simulation results are fully compared with the experimental results. In what follows, the sensitivity analysis is conducted on the key microscopic parameters and microstructure characteristics in numerical samples with laminated characteristics. The results show that the influence of microscopic parameters of the parallel bonding model on macroscopic parameters is related to the layering angle and the face type, and the microstructures and initial cracks of numerical samples can considerably affect the macroscopic mechanical behaviors of the laminated samples. Next, the effect of confining pressure on the mechanical properties of layered shale is also discussed based on the numerical results. These findings highlight the potential of this approach for applications in micro-scaled models and calibration of microscopic parameters to probe mechanical behaviors of the laminated rock.

Performance optimization of lead-free potassium germanium halide based perovskite solar cells: A numerical study

Conventional lead-halide perovskite solar cells (PSCs) have great potential as top contenders for commercial utilization due to their impressive performance. Nevertheless, the stability issues and undue toxicity have limited their widespread use. Consequently, lead-free germanium-based PSCs have materialized as potential substitutes due to their high working efficiency and exceptional sustainability. The current study has examined various configurations of non-toxic inorganic potassium germanium trichloride (KGeCl3) based PSC structure by using different Hole Transport Layers (HTL) and Electron Transport Layers (ETLs) respectively. This work proposes an efficient Ge-based PSC (structure; FTO/MoO3/KGeCl3/WS2/Au), which has been optimized theoretically using SCAPS-1D. The influence of the material parameters, such as the thickness of the absorber layer (nm), donor density (Nd), acceptor density (Na), absorber defect density(Nt), interface layer defect density (IL1& IL2), series resistance (Rs) and shunt resistance (Rsh), and working temperature (K), has been optimized. The open circuit voltage (Voc), current density (Jsc), fill factor (FF), and power conversion efficiency (PCE) of KGeCl3-based PSC have all been commendably optimized. The results indicated WS2 as the most effective ETL for KGeCl3 with MoO3 as an HTL, yielding notable cell performance with Voc of 0.88 V, Jsc of 41.45 mA/cm2, FF of 81.76 %, and PCE of 29.83 %. The outcomes of this simulation study suggest the utilization of KGeCl3 as the absorber layer, in conjunction with WS2 and MoO3 as advanced ETL and HTL layers, which pays the way for continued development and optimization of Ge-based PSCs for potential applications.

The Tepsi Ultrabasic Intrusion, the Northern Part of the Lapland–Belomorian Belt, Kola Peninsula, Russia

The Tepsi ultrabasic body is located in the northeastern Fennoscandian Shield close to the junction of the Serpentinite Belt–Tulppio Belt (SB–TB) with suites of the Lapland–Belomorian Belt (LBB) of Paleoproterozoic age. The body is a deformed laccolith that has tectonic contacts with Archean rocks. Its primary textures and magmatic parageneses are widely preserved. Fine-grained olivine varies continuously from Fo90.5 to Fo65.4. The whole-rock variations in MgO, Fe2O3, SiO2, and other geochemical data are also indicative of a significant extent of differentiation. Compositional variations were examined in the grains of calcic and Mg-Fe amphiboles, clinochlore, micas, plagioclase, members of the chromite–magnetite series, ilmenite, apatite, pentlandite, and a number of other minor mineral species. Low-sulfide disseminated Ni-Cu-Co mineralization occurred sporadically, with the presence of species enriched in As or Bi, submicrometric grains rich in Pt and Ir, or diffuse zones in pentlandite enriched in (Pd + Bi). We recognize two series: the pentlandite series (up to 2.5–3 wt.% Co) and the cobaltpentlandite series (~1 to ~8 apfu Co). The latter accompanied serpentinization. The two series display differences in their substitutions: Ni ↔ Fe and Co → (Ni + Fe), respectively. Relative enrichments in H2O, Cl, and F, observed in grains of apatite (plus high contents of Cl in hibbingite or parahibbingite), point to the abundance of volatiles accumulated during differentiation. We provide the first documentation of scheelite grains in ultrabasic rocks, found in evolved olivine-rich rocks (Fo77–72). We also describe unusual occurrences of hypermagnesian clinopyroxene associated with tremolite and serpentine. Abundant clusters of crystallites of diopside display a microspinifex texture. They likely predated serpentinization and formed due to rapid crystallization in a differentiated portion of a supercooled oxidized melt or, less likely, fluid, after bulk crystallization of the olivine. We infer that the laccolithic Tepsi body crystallized rapidly, in a shallow setting, and could thus not form megacycles in a layered series or produce a well-organized structure. Our findings point to the existence of elevated PGE-Au-Ag potential in numerous ultrabasic–basic complexes of the SB–TB–LBB megastructure.

Genetic Clustering Algorithm Based on the Division and Combination of Layer Series of Development

Petroleum is a critical industrial material. In the process of oilfield development, the Fisher’s optimal segmentation method is often used to solve the problem of division and combination of layer series of development. However, when encountering the problem of long samples, this method has particularly obvious drawbacks due to the high storage requirements of the calculation process. Therefore, in practical work, the Fisher’s optimal binary segmentation method is generally used instead. Although it avoids storage problems, it is prone to falling into local optima. On the basis of analyzing the shortcomings of Fisher’s optimal segmentation and optimal binary segmentation algorithms, this paper processes a genetic clustering algorithm. This algorithm overcomes the problem of Fisher’s optimal binary segmentation algorithm easily falling into local optima and solves the problem of high storage capacity requirements in the calculation process of Fisher’s optimal segmentation algorithm. Taking the data of 17 subzones in S-2 8-11 sand groups of the Shahejie Formation of the Lower Tertiary in the Dongxin area as an example, this algorithm is applied to divide and combine layer series of development. The experimental results show that the algorithm’s partitioning results are reasonable and can optimize the selection of development layers and provide decision support for the production of oil and gas resources.

A Denoising Convolutional Autoencoder for SNR Enhancement in Chemical Exchange Saturation Transfer imaging: (DCAE-CEST).

To develop a SNR enhancement method for chemical exchange saturation transfer (CEST) imaging using a denoising convolutional autoencoder (DCAE), and compare its performance with state-of-the-art denoising methods. The DCAE-CEST model encompasses an encoder and a decoder network. The encoder learns features from the input CEST Z-spectrum via a series of 1D convolutions, nonlinearity applications and pooling. Subsequently, the decoder reconstructs an output denoised Z-spectrum using a series of up-sampling and convolution layers. The DCAE-CEST model underwent multistage training in an environment constrained by Kullback-Leibler divergence, while ensuring data adaptability through context learning using Principal Component Analysis processed Z-spectrum as a reference. The model was trained using simulated Z-spectra, and its performance was evaluated using both simulated data and in-vivo data from an animal tumor model. Maps of amide proton transfer (APT) and nuclear Overhauser enhancement (NOE) effects were quantified using the multiple-pool Lorentzian fit, along with an apparent exchange-dependent relaxation metric. In digital phantom experiments, the DCAE-CEST method exhibited superior performance, surpassing existing denoising techniques, as indicated by the peak SNR and Structural Similarity Index. Additionally, in vivo data further confirms the effectiveness of the DCAE-CEST in denoising the APT and NOE maps when compared to other methods. While no significant difference was observed in APT between tumors and normal tissues, there was a significant difference in NOE, consistent with previous findings. The DCAE-CEST can learn the most important features of the CEST Z-spectrum and provide the most effective denoising solution compared to other methods.

Simulation‐Based Performance Analysis of Lead‐Free Bismuth Perovskite Solar Cells: A Comparative Study of Cs3Bi2I9 and (CH3NH3)3Bi2I9 ‐based Perovskite Solar Cells

AbstractPerovskite solar cells (PSCs) have emerged as promising candidates in PV research due to their exceptional photovoltaic properties. However, the toxicity and environmental concerns associated with lead‐based perovskites have led to the exploration of lead‐free alternatives. In this study, the performance of lead‐free bismuth PSCs, specifically PSCs based on Cesium Bismuth Iodide (Cs3Bi2I9) and Methyl Ammonium Bismuth Iodide (MA3Bi2I9), is investigated. Numerical simulations using the solar cell capacitance simulator (SCAPS) are conducted to comprehensively analyze the influence of key parameters, including the band‐to‐band radiative recombination rate, the absorber layer defect density, the absorber layer/electron transport layer (ETL) interface defect density, the absorber layer/hole transport layer interface (HTL) defect density, operating temperatures, and series and shunt resistances, and to optimize the proposed PSCs accordingly. The simulation results demonstrate a significant impact of these key parameters on the performance of Cs3Bi2I9 and MA3Bi2I9 PSCs. The optimized Cs3Bi2I9‐based PSC exhibited notable performance characteristics, including a PCE of 13.81%, a Voc of 1.16 V, a Jsc of 18.14 mA cm−2, and FF of 65.51%. In contrast, the MA3Bi2I9‐based PSC demonstrated relatively lower performance, with a PCE of 11.82%, Voc of 1.14 V, Jsc of 18.06 mA cm−2, and FF of 57.33%. The study on the defect density at the interfaces revealed the performance of PSCs is predominantly influenced by defects at the front interface (ETL/Absorber) rather than the rear interface (HTL/Absorber). These results provide valuable insights for the experimental design and optimization of lead‐free bismuth PSCs.

Investigating the potential of WO3 and WS2 as Cd-free buffer layers in Sb2Se3-Based thin-film solar cells: A numerical study with SCAPS-1D software

In this numerical study, the performance of thin-film solar cells (TFSCs) based on Sb2Se3 with WO3 and WS2 materials as Cd-free buffer layers was investigated using SCAPS-1D software. WO3 and WS2 were chosen for their suitable band gaps, good electrical conductivity, and optical transparency. The proposed solar cell structures, Au/Sb2Se3/WO3/ITO and Au/Sb2Se3/WS2/ITO were theoretically examined, considering various factors such as conduction band offset, absorber and buffer layer thickness, doping concentrations, series and shunt resistances, temperature, activation energy, and C–V characteristic. The conduction band offset at the absorber/buffer interface showed spike-like configurations, with values of 0.38 eV and 0.23 eV for the WO3 and WS2 buffer layers, respectively. The optimized thickness for the absorber layer in both structures was 1 μm, while for WO3 and WS2 buffer layers, it was 0.1 μm and 0.05 μm, respectively. The optimized acceptor and donor doping concentrations were 1 × 1016 cm−3 and 1 × 1018 cm−3, respectively. The efficiency of the proposed photovoltaic devices was found to be 9.538 % (with Voc = 0.561 V, Jsc = 30.856 mA/cm2, FF = 55.84 %) and 10.151 % (with Voc = 0.558 V, Jsc = 29.189 mA/cm2, FF = 62.34 %) for structures with WO3 and WS2 buffer layers, respectively. These results suggest that using non-toxic materials like WO3 and WS2 as buffer layers can be an efficient and environmentally friendly alternative to toxic CdS for fabricating cost-effective and highly efficient Sb2Se3-based TFSCs.

AUTOMATED PNEUMONIA IDENTIFICATION THROUGH CNN-BASED ANALYSIS

Pneumonia, a condition caused by infectious agents such as bacteria, viruses, fungi, or parasites, results in lung infections and the accumulation of pus in affected tissues. Incorrect diagnosis or improper treatment can significantly impact a patient's quality of life. This project focuses on the precise identification and categorization of pneumonia-afflicted patients through the analysis of their chest X-rays. Leveraging advancements in deep learning, healthcare experts can make more accurate diagnostic decisions for various illnesses. This study presents an innovative approach utilizing Convolutional Neural Networks (CNN) to predict and distinguish between patients affected by pneumonia and those who are not, based on chest X-ray images. The methodology involves a series of convolutional and max pooling layers activated using the ReLU activation function. Subsequently, the processed data is passed through dense layers, culminating in the activation of the output neuron through the sigmoidal function. During the training process, the model exhibits increasing accuracy and decreasing loss, demonstrating its effectiveness. To prevent overfitting, data augmentation techniques are applied before model fitting. These strategies collectively enhance the robustness and reliability of the deep learning models, resulting in accurate and persuasive detection of pneumonia from chest X-ray images. Keywords: Pneumonia, CNN, VGG-16, VGG-19, Chest X-rays, Classification, Deeep learning, Data augmenatation, ReLU, softmax.

VIDEO FORGERY IDENTIFICATION APPLICATION

The rapid advancement of deepfake technology has raised significant concerns about the authenticity of visual content. Deep fake videos, which convincingly superimpose one person's likeness onto another's, can be used for both harmless entertainment and malicious misinformation. Detecting these manipulated videos is crucial for maintaining trust and accuracy in media. In this study, we propose a novel approach for deep fake video detection using deep learning techniques, coupled with a user-friendly graphical user. Our methodology involves training a deep neural network using a large dataset of both real and deep fake videos. These features are then fed in to a series of convolutional and recurrent layers to capture both spatial and temporal information. Keywords: Superimpose, Misinformation, Neural Network, convolutional, spatial.

Survey on Silentinterpreter : Analysis of Lip Movement and Extracting Speech using Deep Learning

Lip reading is a complex but interesting path for the growth of speech recognition algorithms. It is the ability of deciphering spoken words by evaluating visual cues from lip movements. In this study, we suggest a unique method for lip reading that converts lip motions into textual representations by using deep neural networks. Convolutional neural networks are used in the methodology to extract visual features, recurrent neural networks are used to simulate temporal context, and the Connectionist Temporal Classification loss function is used to align lip features with corresponding phonemes. The study starts with a thorough investigation of data loading methods, which include alignment extraction and video preparation. A well selected dataset with video clips and matching phonetic alignments is presented. We select relevant face regions, convert frames to grayscale, then standardize the resulting data so that it can be fed into a neural network. The neural network architecture is presented in depth, displaying a series of bidirectional LSTM layers for temporal context understanding after 3D convolutional layers for spatial feature extraction. Careful consideration of input shapes, layer combinations, and parameter selections forms the foundation of the model's design. To train the model, we align predicted phoneme sequences with ground truth alignments using the CTC loss. Dynamic learning rate scheduling and a unique callback mechanism for training visualization of predictions are integrated into the training process. After training on a sizable dataset, the model exhibits remarkable convergence and proves its capacity to understand intricate temporal correlations. Through the use of both quantitative and qualitative evaluations, the results are thoroughly assessed. We visually check the model's lip reading abilities and assess its performance using common speech recognition criteria. It is explored how different model topologies and hyperparameters affect performance, offering guidance for future research. The trained model is tested on external video samples to show off its practical application. Its accuracy and resilience in lip-reading spoken phrases are demonstrated. By providing a deep learning framework for precise and effective speech recognition, this research adds to the rapidly changing field of lip reading devices. The results offer opportunities for additional development and implementation in various fields, such as assistive technologies, audio-visual communication systems, and human-computer interaction.

DBDNMF: A Dual Branch Deep Neural Matrix Factorization method for drug response prediction.

Anti-cancer response of cell lines to drugs is in urgent need for individualized precision medical decision-making in the era of precision medicine. Measurements with wet-experiments is time-consuming and expensive and it is almost impossible for wide ranges of application. The design of computational models that can precisely predict the responses between drugs and cell lines could provide a credible reference for further research. Existing methods of response prediction based on matrix factorization or neural networks have revealed that both linear or nonlinear latent characteristics are applicable and effective for the precise prediction of drug responses. However, the majority of them consider only linear or nonlinear relationships for drug response prediction. Herein, we propose a Dual Branch Deep Neural Matrix Factorization (DBDNMF) method to address the above-mentioned issues. DBDNMF learns the latent representation of drugs and cell lines through flexible inputs and reconstructs the partially observed matrix through a series of hidden neural network layers. Experimental results on the datasets of Cancer Cell Line Encyclopedia (CCLE) and Genomics of Drug Sensitivity in Cancer (GDSC) show that the accuracy of drug prediction exceeds state-of-the-art drug response prediction algorithms, demonstrating its reliability and stability. The hierarchical clustering results show that drugs with similar response levels tend to target similar signaling pathway, and cell lines coming from the same tissue subtype tend to share the same pattern of response, which are consistent with previously published studies.

A fusion architecture to deliver multipurpose mobile health services

Mobile Health (mHealth) services typically make use of customized software architectures, leading to development-dependent fragmentation. Nevertheless, irrespective of their specific purpose, most mHealth services share common functionalities, where standard pieces could be reused or adapted to expedite service deployment and even extend the follow-up of appearing conditions under the same service. To harness compatibility and reuse, this article presents a data fusion architecture proposing a common design framework for mHealth services. An exhaustive mapping of mHealth functionalities identified in the literature serves as starting point. The architecture is then conceptualized making use of the Joint Directors of Laboratories (JDL) data fusion model. The aim of the architecture is to exploit the multi-source data acquisition capabilities supported by smartphones and Internet of Things devices, and artificial intelligence-enabled feature fusion. A series of interconnected fusion layers ensure streamlined data management; each layer is composed of microservices which may be implemented or omitted depending on the specific goals of the healthcare service. Moreover, the architecture considers essential features related to authentication mechanisms, data sharing protocols, practitioner-patient communication, context-based notifications and tailored visualization interfaces. The effectiveness of the architecture is underscored by its instantiation for four real cases, encompassing risk assessment for youth with mental health issues, remote monitoring for SARS-CoV-2 patients, liquid intake control for kidney disease patients, and peritoneal dialysis treatment support. This breadth of applications exemplifies how the architecture can effectively serve as a guidance framework to accelerate the design of mHealth services.